Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Guardrails for Heavy-Duty Vehicle Autonomous Driving: Verified Planning and Control in AI-Based Architectures

Reference number
Coordinator Traton AB
Funding from Vinnova SEK 7 144 585
Project duration June 2026 - August 2030
Status Ongoing
Venture Safe automated driving – FFI
Call Traffic-safe automation - FFI - spring 2026

Purpose and goal

The project aims to develop Guardrails and Verified Planning & Control methods that make AI-based autonomous driving for heavy-duty vehicles safer and more robust. The goal is to supervise nominal AI driving behavior with independent safety constraints, handle uncertainty and interaction with other road users, ensure feasible fallback behavior, and validate the methods in simulation for future ADAS and higher automation applications.

Expected effects and result

Expected results are a validated Guardrails-Verified Planning & Control architecture, methods for translating rules and uncertainty into enforceable safety constraints, and robust motion planning/control algorithms for heavy-duty vehicles. The effects are improved safety assurance for AI-based autonomous driving, reduced deployment risk, stronger TRATON/KTH competence, scientific publications, and reusable tools for ADAS and future higher automation.

Planned approach and implementation

The project will be implemented through coordinated work packages covering project management, literature review, architecture and interface definition, Guardrails design, verified motion planning/control, and experimental validation. Methods will be developed jointly by TRATON and KTH, integrated in representative autonomy toolchains, and evaluated using scenario-based simulation, HDV vehicle models, logging, metrics, and iterative steering-group follow-up.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 8 June 2026

Reference number 2026-00791